© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 88268
    Prev
    Next
    INDEX
    Explanations

    up/out/down/off followed by in/into/with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oup
    -0.10
    adh
    -0.09
    linger
    -0.09
     Gamb
    -0.09
     Shard
    -0.09
    fade
    -0.08
     untouched
    -0.08
     imper
    -0.08
     builtin
    -0.08
     Herm
    -0.08
    POSITIVE LOGITS
    /out
    0.11
    ana
    0.11
     by
    0.10
    /shared
    0.10
    edly
    0.10
    /down
    0.10
    /resource
    0.09
    fts
    0.09
    ensively
    0.09
     happening
    0.09
    Activations Density 0.061%

    No Known Activations